Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2457 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.4967. Min Act: -0.0001

Data Index: 988222 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.2058. Min Act: -0.0001

Data Index: 1322221 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.1566. Min Act: -0.0001

Data Index: 391495 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.2937. Min Act: -0.0001

Data Index: 997710 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.1554. Min Act: -0.0001

Data Index: 1331058 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.0299. Min Act: -0.0001

Data Index: 624961 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.0273. Min Act: -0.0001

Data Index: 552474 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.9462. Min Act: -0.0001

Data Index: 709344 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.7720. Min Act: -0.0001

Data Index: 1102675 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.8696. Min Act: -0.0001

Data Index: 118960 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.9223. Min Act: -0.0001

Data Index: 717062 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.2140. Min Act: -0.0001

Data Index: 189226 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.1590. Min Act: -0.0001

Data Index: 82048 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.9616. Min Act: -0.0001

Data Index: 782781 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.4499. Min Act: -0.0001

Data Index: 218952 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.0999. Min Act: -0.0001

Data Index: 557278 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.0056. Min Act: -0.0001

Data Index: 45366 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.8768. Min Act: -0.0001

Data Index: 564035 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.7326. Min Act: -0.0001

Data Index: 890737 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.9800. Min Act: -0.0001

Data Index: 668938 (C4 (Web Text))

Max Activating Token Index: 521